BIGDML-Towards accurate quantum machine learning force fields for materials

Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Currently, MLFFs often introduce tradeoffs that restrict their practical applicability to small subsets of chemical space or require exhaustive...

Full description

Saved in:
Bibliographic Details
Published inNature communications Vol. 13; no. 1; p. 3733
Main Authors Sauceda, Huziel E, Gálvez-González, Luis E, Chmiela, Stefan, Paz-Borbón, Lauro Oliver, Müller, Klaus-Robert, Tkatchenko, Alexandre
Format Journal Article
LanguageEnglish
Published England Nature Publishing Group 29.06.2022
Nature Publishing Group UK
Nature Portfolio
Subjects
Accuracy
Adsorbates
Atomic interactions
Benzene
Building materials
Construction materials
Diffusion coefficient
Electronics industry
Graphene
Interfaces
Learning algorithms
Localization
Machine learning
Metals
Molecular dynamics
Potential energy
Quantum dots
Training
Online AccessGet full text

Cover

More Information
Summary:Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Currently, MLFFs often introduce tradeoffs that restrict their practical applicability to small subsets of chemical space or require exhaustive datasets for training. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning (BIGDML) approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 geometries for materials including pristine and defect-containing 2D and 3D semiconductors and metals, as well as chemisorbed and physisorbed atomic and molecular adsorbates on surfaces. The BIGDML model employs the full relevant symmetry group for a given material, does not assume artificial atom types or localization of atomic interactions and exhibits high data efficiency and state-of-the-art energy accuracies (errors substantially below 1 meV per atom) for an extended set of materials. Extensive path-integral molecular dynamics carried out with BIGDML models demonstrate the counterintuitive localization of benzene-graphene dynamics induced by nuclear quantum effects and their strong contributions to the hydrogen diffusion coefficient in a Pd crystal for a wide range of temperatures.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-022-31093-x